CrewAI
Role-playing agents working as a crew.
High-performance multimodal agents.
Local or cloud · No GPU
Negligible local footprint. GPU only if running a local multimodal model.
Source is public — you can audit it, fork it, and you'll never lose access to your workflows if Agno the company changes direction.
Doesn't require a dedicated GPU — useful on laptops and headless servers.
Native Metal / MPS support — runs on M-series Macs without CUDA gymnastics.
You don't need to read a paper before getting your first result — sensible defaults and a quick install.
This page summarizes upstream documentation, release information, and editorially reviewed catalogue fields. It is not presented as a hands-on benchmark. Verify changing requirements at the official project; report stale data through our corrections channel.
Runs CPU-only — no CUDA / driver gymnastics required.
No dedicated GPU required.
Open-source AND ships an API — easy to integrate, possible to host yourself.
Catalogue entry last updated 65 days ago — re-verification due soon.
Three picks across different tradeoffs — so you don't end up with three near-clones of Agno.
Agno (formerly Phidata) is a Python framework for building multimodal agents with memory, knowledge, and tools. Notable for being unusually fast (~3μs agent instantiation, ~6.5KB RAM) thanks to a tight runtime, and for first-class support for image, audio, and video I/O — not just text.
OSS framework free; Agno Cloud has free tier with paid plans.